CN110210352A - Ship track method for detecting abnormality based on navigation channel model - Google Patents
Ship track method for detecting abnormality based on navigation channel model Download PDFInfo
- Publication number
- CN110210352A CN110210352A CN201910433802.4A CN201910433802A CN110210352A CN 110210352 A CN110210352 A CN 110210352A CN 201910433802 A CN201910433802 A CN 201910433802A CN 110210352 A CN110210352 A CN 110210352A
- Authority
- CN
- China
- Prior art keywords
- navigation channel
- channel model
- data
- ais
- track
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of ship track method for detecting abnormality based on navigation channel model includes the following steps: 1, obtains the history AIS data in seclected time section；Step 2 pre-processes history AIS data；3, pretreated AIS data are extracted with destination and the course line of navigation channel model respectively, by destination and course line respectively as the vertex and side of the figure in graph theory, to form navigation channel model: step 4, to navigation channel model, temporally element is weighted, and obtains final navigation channel model；Whether final navigation channel model is compared by step 5 with track to be detected, occurred in final navigation channel model according to track to be detected to judge whether track is abnormal.The advantages of present invention is based on point algorithm and is based on Trajectory Arithmetic by fusion, has sufficiently excavated the navigation historical law in hot spot region, the behavior pattern and space time information that ship trajectory of having got back leaves；Not only Short Term Anomalous monitoring can be carried out, but also long-term exception monitoring can be carried out.
Description
Technical field
The present invention relates to ships data processing technology fields, abnormal in particular to a kind of ship track based on navigation channel model
Detection method.
Background technique
Under world's age and globalization of economy background, various countries and interzone trade increase, and marine transportation industry obtains numerous
Rong Fazhan, while navigation safety at sea hidden danger also gradually highlights.On the one hand, Present Global ships quantity is huge and increasingly increases,
Complexity that Description of Ship is various and course line interlocks so that the motor behavior of ship it is difficult to predict, security context there is it is unstable because
Element；On the other hand, since the capacity in harbour and navigation channel is limited, navigation channel is congested in traffic, and over-burden in course line, with increasingly increased ship
Contradiction between oceangoing ship quantity displays, and it is huge that the navigation channel and course line being staggeredly distributed in length and breadth are that maritime administration and exception monitoring are brought
Big challenge.
Ship exception monitoring technology is the major way to exercise supervision to ship, monitors sea using exception monitoring technology
The generation of accident is rescued and reduced in time to distress situation existing for ship；It was found that illegal ship behavior, strike is marine illegal
Criminal offence achievees the purpose that protect China's maritime affairs equity and territorial waters safety.
AIS (Automatic Identification System, ship automatic identification system) data accumulation amount is big, interior
Hold comprehensively, with a high credibility, the potential value of AIS data is constantly excavated and applied in recent years.By the behavior for combining ship
Pattern feature is counted, analyzed and is excavated the exception monitoring, it can be achieved that ship to AIS data.
The exception monitoring of ship refers to the legal of multidate information (longitude and latitude, the course, speed of a ship or plane etc.) progress to target ship
Property monitoring, can find specified vessel abnormal conditions that may be present in time.
Currently to ship exception monitoring research use algorithm mainly have trajectory clustering Artificial Potential Field, Bayesian model,
Kalman filtering, Density Estimator, Gaussian process etc..
1, based on the algorithm of trajectory clustering: by being clustered and being identified to abnormal behaviour, completing to ship abnormal behaviour
Automatic alarm.
2, based on the algorithm of Artificial Potential Field: indicating maritime traffic model using Artificial Potential Field and carry out exception monitoring, can answer
For different scene such as high sea, harbour, rivers etc., discovery traffic rules are extracted, navigation channel can be made to be visualized.
3, based on the algorithm of Bayesian model: the ship information distribution situation by analysing selected waters, according to its probability point
Cloth constructs the ship abnormal behaviour monitoring model based on NB Algorithm.Dynamic and static shellfish are established using AIS data
This model of leaf, available abnormal conditions, by improving coverage rate in conjunction with dynamic-static model.
4, based on the algorithm of Kalman filtering: in conjunction with the characteristics of AIS data, designing the exception based on Kalman filtering algorithm
Navigate line monitoring system.
5, based on the algorithm of Density Estimator: it is for statistical analysis to the history AIS data of ship, excavate inland navigation craft
Motor pattern establishes abnormal behaviour monitoring algorithm based on this, can longitude and latitude to ship and zone velocity be monitored.
6, based on the algorithm of Gaussian process: identifying abnormal conditions by defining normal mode, that is, first pass through Gaussian process
Maritime affairs data model is obtained, exception monitoring is then carried out by model.
In general, it carries out exception monitoring to the ship with complete trajectory to be easily achieved, but since marine environment is changeable,
Especially off-lying sea area, communication mechanism is unsmooth, and in the case where can not obtaining real-time, continuous AIS data, most of algorithms are difficult
Reach satisfactory application effect.Therefore, it is necessary to design a kind of algorithm that can be suitably used for complex scene, i.e., to object ship
It can be effectively carried out exception monitoring in the case that oceangoing ship Information amount is different.
Summary of the invention
Present invention aim to provide a kind of ship track method for detecting abnormality based on navigation channel model, this method needle
Problem above and deficiency the shortcomings that making up wherein, are sufficiently dug the advantages of being based on point algorithm by fusion and be based on Trajectory Arithmetic
The navigation historical law in hot spot region is dug, the behavior pattern and space time information that ship trajectory of having got back leaves；It both can be with
Short-term exception monitoring is carried out, and long-term exception monitoring can be carried out.
In order to achieve this, a kind of ship track method for detecting abnormality based on navigation channel model designed by the present invention,
It is characterized in that, it includes the following steps:
Step 1: obtaining the history AIS data in seclected time section；
Step 2: deletion redundant data, erased noise data being carried out to history AIS data, divide uncertain track, to rail
The pretreatment of mark sampling and trajectory interpolation；
Step 3: according to the definition to navigation channel model, pretreated AIS data being extracted with the boat of navigation channel model respectively
Point and course line, by destination and course line respectively as the vertex and side of the figure in graph theory, the navigation channel Lai Zucheng model:
Step 4: temporally element is weighted the navigation channel model obtained to step 3, obtains final navigation channel model；
Step 5: final navigation channel model being compared with track to be detected, according to track to be detected in final navigation channel
Whether occur in model to judge whether track is abnormal, if occurring in final navigation channel model, for normal trace, otherwise
For abnormal track.
Compared with prior art, the invention has the following advantages:
1, the present invention solves ship motor behavior complexity using the structure of navigation channel model, and course line distribution staggeredly in length and breadth and obtains
The information taken is imperfect to cause exception to be difficult to the problem of monitoring, and indicates destination (harbour, busy navigation channel joint and navigation channel with model
The important areas such as turning point) and navigation route, and it is based on navigation channel model realization ship exception monitoring.
2, the present invention uses AIS data prediction mode, not true by deletion redundant data, erased noise data, segmentation
Fixed track, to track sampling and interpolation, substantially increase the availability of data, increase the detection accuracy of this method.Pretreatment
Method uses parallel form, can give full play to the advantage of multiserver multiprocessing core, improves pre- place using distributed platform
Manage speed.
3, the present invention is asked using what the navigation channel model extraction algorithm that temporally weights solved that navigation channel distribution changes over time
Topic update model can by addition data；Using it is a kind of based on grid can Parallel Algorithm improve efficiency, make the algorithm can
Read group total environment is needed applied to different.
Detailed description of the invention
Fig. 1 is the principle of the present invention block diagram.
Fig. 2 is navigation channel model schematic；
In Fig. 2, ABCDEF is node, the destination in model of navigating；Line between them is side, in model of navigating
Course line, destination and course line collectively constitute navigation channel model.
Specific embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail:
A kind of ship track method for detecting abnormality based on navigation channel model that the present invention designs, as shown in Figure 1, it includes such as
Lower step:
Step 1: obtaining the history AIS data in seclected time section, the abnormality detection of ship track from Shipping service quotient
Substantially judge according further to the behavior pattern of ship, needs historical record as the standard contrasted；
Step 2: deletion redundant data, erased noise data being carried out to history AIS data, divide uncertain track, to rail
The pretreatment of mark sampling and trajectory interpolation, obtains without redundancy and noise, and improve the AIS data of arithmetic accuracy, to improve
The accuracy of exception monitoring result, is influenced by ship navigation state, and the sparsity of the point in track is different, ship running speed
Fast place forms sparse, and the point that the slow place of travel speed is formed is intensive, will be greatly reduced algorithm if without processing
Operational efficiency；
Step 3: according to the definition to navigation channel model, pretreated AIS data being extracted with the boat of navigation channel model respectively
Point and course line, by destination and course line respectively as the vertex and side of the figure in graph theory, the navigation channel Lai Zucheng model describes for convenience
Marine ships navigation rule, extracts harbour, busy navigation channel intersection and navigation channel turning point etc. between vital areas and its area
Navigation route, realize ship exception monitoring technology, using the concept of navigation channel model, as shown in Figure 2.Wherein each section indicates
Meaning is respectively as follows:
(1) destination (node of corresponding diagram, filled circles indicate) indicates the primary location in the model of navigation channel, including each port
Mouth, busy course line joint and break of course line course change etc.；
(2) course line (directed edge of corresponding diagram, line segment indicate) indicates existing relevance between each primary location.Its
In, the weight on side indicates the busy extent in course line in figure:
Step 4: temporally element is weighted the navigation channel model obtained to step 3, obtains final navigation channel model；
Step 5: final navigation channel model being compared with track to be detected, according to track to be detected in final navigation channel
Whether occur in model to judge whether track is abnormal, if occurring in final navigation channel model, for normal trace, otherwise
For abnormal track.
In the step 2 of above-mentioned technical proposal, delete in redundant data treatment process, redundant data refers to be weighed in the database
Multiple data, since ship has unique MMSI (Maritime Mobile Service Identify, Waterborne movable communication
Service identification) coding, and the MMSI with timestamp of repeated data are identical in AIS database, and AIS redundant data is defined as
The data for possessing identical MMSI and timestamp in AIS database only retain a record when being judged as redundant data；
In AIS database, it is identical with timestamp that there are MMSI, and other attribute (such as longitude and latitude) discrepant feelings
Condition.This is not belonging to proper redundant data, but meets the definition of AIS redundant data, because such case is shown
Same ship appears in different positions at same time point, and manifest error is generated on track, is applied on algorithm and also can
Influence is deleted together as a result, being classified to redundant data herein.The fortune of algorithm not only can be improved in this succinct definition method
Line efficiency (without successively comparing attribute value), and do not have an adverse effect to final result.
In erased noise data procedures, noise data refers to the data in data there are attribute abnormal, and AIS noise data is
The abnormal number of AIS longitude attributes, longitude attribute, speed of a ship or plane attribute or course attribute not in the normal range (NR) of each corresponding attribute
According to, above-mentioned AIS noise data is deleted (such as the normal range (NR) of speed of a ship or plane attribute is 0~30 section, speed of a ship or plane of emerging is 56 sections
Data are exactly abnormal data)；Due in AIS data MMSI and timestamp spatial distribution is not influenced, not the noise the considerations of
In range, what the identification of noise data mainly judged according to the speed of a ship or plane and the two attributes of course；
Since the density of the base station AIS is too low or other communication failure factors, the AIS information that ship issues under operational configuration
It is not all to be received to record, especially navigation is to from the farther away sea area in coastline, it may appear that the signal that ship issues
Continuous a period of time all unwritten phenomenon.It therefore is when having one or more in track data by uncertain track definition
Between record missing in section, lead to not the track for determining true path.
Influence when lack part appears among navigation channel in uncertain track to algorithm is smaller；It is turned when appearing in navigation channel
When at point, the navigation channel result that algorithm can be made to obtain is deformed；When land is crossed at the both ends of lack part, algorithm can be made to cause obviously
Mistake；
Divide uncertain track to refer to when the distance of AIS data point two neighboring in track is more than the spacing threshold being arranged
When, the track of two neighboring AIS data point is divided into two sections of tracks, and two sections of tracks are respectively less than and are equal to spacing threshold, i.e., will
One inaccurate long track is divided into two accurate short tracks, wherein spacing threshold refers to the carry out track segmentation of setting
Capacity-threshold；The spacing threshold is all two neighboring AIS data points in track apart from twice of median.
Track is sampled as the track AIS carrying out value according to preset track consecutive points interval；
Trajectory interpolation is to be inserted into when distance between two points meet interpolation distance condition in the track AIS according to linear interpolation method
Corresponding AIS data, the common linear interpolation of interpolation rule, Lagrange Polynomial interpolating and Newton interpolation etc., due to needing
It wants to be respectively less than the maximum spacing for carrying out track segmentation at interpolation, that is, needs the distance of interpolation little, therefore selected linear interpolation herein
Method.
The interpolation distance condition is interpolation apart from interpolation critical distance, (critical distance is distance between tracing point
Median, that is, most go out the most distance of occurrence) do not known between the maximum spacing set in track to segmentation.
Following purpose is mainly reached in pretreatment:
1, the accuracy for improving data, reduces the adverse effect of noise data；
2, increase the integrality of data, improve the outcome quality of model extraction algorithm；
3, the complexity of data, the runing time of reduced-order models extraction algorithm are reduced.
Wherein, redundant data is deleted, cancelling noise data are carried out by unit data of every AIS；Divide, is right in track
Track carry out sampling and carry out interpolation to track to be carried out respectively as unit of track.Delete redundant data, cancelling noise number
According to the accuracy that data can be improved, the adverse effect of noise data is reduced；Track segmentation can increase data to track progress interpolation
Integrality, improve model extraction algorithm outcome quality；Data volume can be reduced by sampling to track, and reduced-order models extract
The runing time of algorithm.
In the step 3 of above-mentioned technical proposal, mentioning for the destination of navigation channel model is extracted respectively to pretreated AIS data
Standard is taken to be determined by following formula:
P refers to the current corresponding coordinate points of AIS data point, and WP refers to that this situation is judged as that destination, Q refer to other AIS data points,
α is that (effect of the threshold value is that how many coordinate points are gathered at one piece, just meeting for the amount thresholds of the corresponding coordinate points of AIS data point
It draws attention, assigns him as destination, taken 50) in the present embodiment, distance is distance function；AISdata is all AIS numbers
According to it is not destination that noise, which gives directions P, if others, which refers to, is unsatisfactory for above situation.
The range formula of use are as follows:
Wherein, Δ λ indicates the difference of longitude of P, Q two o'clock；The longitude of P, Q two o'clock is respectively indicated,Indicate P, Q
The difference of latitude of two o'clock, R indicate earth radius.
The position that destination is determined using trellis algorithm, using each AIS data point of known history AIS data as boat
The candidate point of point position, by Δ lon (10km) is grown into the corresponding navigation area division of history AIS data, width is Δ lat
Multiple grids of (10km) calculate separately to obtain the destination in each grid, then together by the destination in each grid
Come, finally obtains the destination data in whole region.The selection needs of side length of element are adjusted specific sea area and data, if
The Bian Tai great of grid will cause point distribution extremely unevenness in each grid, influence calculated performance；If choosing too small, many nets
Point in lattice is very little so that it cannot be identified as destination.
In above-mentioned technical proposal, current way point information only has position and radius information, by the AIS number in destination
AIS data point average coordinates, course over ground and speed on the ground information in destination coverage can be obtained according to analysis is carried out.
In the step 4 of above-mentioned technical proposal, the navigation channel model specific side that temporally element is weighted that step 3 is obtained
Method are as follows:
When only history AIS data, or when applying navigation channel model algorithm for the first time, step is weighted are as follows:
1, using the AIS data belonged on the same day as a subdata；
2, subdata is respectively converted into corresponding navigation channel model submodel in chronological order；
3, it is temporally weighted by all submodels and constitutes final navigation channel model, wherein the time, more late to account for weight bigger.
When the navigation channel model of existing history AIS data acquisition, when needing to add new AIS data and carrying out more new model, weighting step
Suddenly are as follows:
1.1, usage history AIS data obtain old navigation channel model；
1.2, updated navigation channel model is obtained using new AIS data；
1.3, by old navigation channel model and updated navigation channel model average weighted, (average weighted is new and old two navigation channel models
Weight is identical, is all 0.5), to obtain final navigation channel model, so not only included the influence of historical data, but also have data increased
Variation.
In the step 4 of above-mentioned technical proposal, history AIS data are substituted into final navigation channel model, are obtained based on navigation channel mould
The cruising formation of type counts the frequent behavior pattern of ship.It is influenced by reasons such as season, tide, policies, the boat in practical application
Road course line be it is continually changing at any time, navigation channel model will also have the ability updated at any time.This method proposition is temporally joined
Number method of weighting makes navigation channel model evolve, and update model can at any time.
Temporally element is weighted formula and may be expressed as: step 4 navigation channel model
Wherein,Indicate that the A attribute of i-th of destination, n are the quantity of destination, t is time variable, and current is indicated
Current time, weight are weighting function,Indicate value of the A attribute in time t of i-th of destination；S.t. it indicates
Above formula meets the following conditions.
In the step 3 of above-mentioned technical proposal, course line (Navigation Line, abbreviation NL) refers between two destinations of connection
Route, described with a triple NL=(F, T, W), wherein F is the destination that is driven out to of course line；T is the boat that course line is driven into
Point, F and T constitute the direction in course line, i.e. direction isW is the number that course line occurred.
By calculating the destination of the track connection in database, existing course line between available connected destination.
The abnormality detection of ship track needs historical record to make substantially according further to the behavior pattern of ship come what is judged
For according to standard, common AIS data include longitude, latitude, time, ship MMSI, course, the speed of a ship or plane, and source includes
Bank base AIS data and satellite AIS data, wherein bank base data because ship and base station number it is more, data volume is larger, but only includes
Coastal waters data；And satellite data mainly includes ocean part ship information, is influenced by satellite transit mechanism, data volume is smaller,
Include ocean data.Bank base data complement one another with satellite data.
The present invention solves ship motor behavior complexity because using the structure of navigation channel model, and course line distribution interlocks
In length and breadth with the information of acquisition is imperfect causes abnormal to be difficult to the problem of monitoring.
The present invention uses AIS data prediction mode, does not know by deleting redundant data, erased noise data, dividing
Track increases the detection accuracy of this method so substantially increasing the availability of data to track sampling and interpolation.Because
Preprocess method uses parallel form, so the advantage of multiserver multiprocessing core can be given full play to, it is flat using distribution
Platform improves pre-treating speed.
The content that this specification is not described in detail belongs to the prior art well known to professional and technical personnel in the field.
Claims (9)
1. a kind of ship track method for detecting abnormality based on navigation channel model, which is characterized in that it includes the following steps:
Step 1: obtaining the history AIS data in seclected time section；
Step 2: deletion redundant data being carried out to history AIS data, erased noise data, the uncertain track of segmentation, track is adopted
The pretreatment of sample and trajectory interpolation；
Step 3: according to the definition to navigation channel model, to pretreated AIS data extract respectively navigation channel model destination and
Course line, by destination and course line respectively as the vertex and side of the figure in graph theory, the navigation channel Lai Zucheng model:
Step 4: temporally element is weighted the navigation channel model obtained to step 3, obtains final navigation channel model；
Step 5: final navigation channel model being compared with track to be detected, according to track to be detected in final navigation channel model
In whether occur to judge whether track abnormal, is otherwise different for normal trace if occurring in final navigation channel model
Normal practice mark.
2. the ship track method for detecting abnormality according to claim 1 based on navigation channel model, it is characterised in that: step 2
In middle deletion redundant data treatment process, redundant data refers to duplicate data in the database, since ship has uniquely
MMSI coding, and the MMSI with timestamp of repeated data are identical in AIS database, and AIS redundant data is defined as in AIS number
According to the data for possessing identical MMSI and timestamp in library, when being judged as redundant data, only retain a record；
In erased noise data procedures, noise data refers to the data in data there are attribute abnormal, and AIS noise data is AIS
The abnormal data of longitude attributes, longitude attribute, speed of a ship or plane attribute or course attribute not in the normal range (NR) of each corresponding attribute,
Above-mentioned AIS noise data is deleted；
Divide uncertain track to refer to when the distance of AIS data point two neighboring in track is more than the spacing threshold of setting, it will
The track of two neighboring AIS data point is divided into two sections of tracks, and two sections of tracks are respectively less than and are equal to spacing threshold, wherein spacing
Threshold value refers to the capacity-threshold of the progress track segmentation of setting；
Track is sampled as the track AIS carrying out value according to preset track consecutive points interval；
Trajectory interpolation is to be inserted into accordingly when distance between two points meet interpolation distance condition in the track AIS according to linear interpolation method
AIS data.
3. the ship track method for detecting abnormality according to claim 2 based on navigation channel model, it is characterised in that: described to insert
Value distance condition is interpolation distance between the maximum spacing that interpolation critical distance is set into the uncertain track of segmentation.
4. the ship track method for detecting abnormality according to claim 1 based on navigation channel model, it is characterised in that: step 3
In, the extraction standard for the destination that pretreated AIS data extract navigation channel model respectively is determined by following formula:
Wherein, P refers to the current corresponding coordinate points of AIS data point, and WP refers to that this situation is judged as that destination, Q refer to other AIS data
Point, α are the amount threshold of the corresponding coordinate points of AIS data point, and distance is distance function；AISdata is all AIS numbers
According to it is not destination that noise, which gives directions P, if others, which refers to, is unsatisfactory for above situation；
The range formula of use are as follows:
Wherein, Δ λ indicates the difference of longitude of P, Q two o'clock；The longitude of P, Q two o'clock is respectively indicated,Indicate P, Q two o'clock
Difference of latitude, R indicate earth radius；
The position that destination is determined using trellis algorithm, using each AIS data point of known history AIS data as destination position
The corresponding navigation area of history AIS data is divided and grows into Δ lon, multiple grids that width is Δ lat by the candidate point set, point
The destination in each grid is not calculated, then the destination in each grid is gathered, finally obtains whole region
Interior destination data.
5. the ship track method for detecting abnormality according to claim 4 based on navigation channel model, it is characterised in that: current
Way point information only has position and radius information, and destination coverage can be obtained by carrying out analysis to the AIS data in destination
Interior AIS data point average coordinates, course over ground and speed on the ground information.
6. the ship track method for detecting abnormality according to claim 1 based on navigation channel model, it is characterised in that: the step
In rapid 4, temporally element is weighted for the navigation channel model that obtains to step 3 method particularly includes:
When only history AIS data, or when applying navigation channel model algorithm for the first time, step is weighted are as follows:
1, using the AIS data belonged on the same day as a subdata；
2, subdata is respectively converted into corresponding navigation channel model submodel in chronological order；
3, it is temporally weighted by all submodels and constitutes final navigation channel model, wherein the time, more late to account for weight bigger；
When the navigation channel model of existing history AIS data acquisition, when needing to add new AIS data and carrying out more new model, step is weighted are as follows:
1.1, usage history AIS data obtain old navigation channel model；
1.2, updated navigation channel model is obtained using new AIS data；
1.3, by old navigation channel model and updated navigation channel model average weighted, final navigation channel model is obtained.
7. the ship track method for detecting abnormality according to claim 6 based on navigation channel model, it is characterised in that: the step
In rapid 4, history AIS data are substituted into final navigation channel model, obtain the cruising formation based on navigation channel model, count the frequency of ship
Numerous behavior pattern.
8. the ship track method for detecting abnormality according to claim 1 based on navigation channel model, it is characterised in that: described to go through
History AIS data include longitude, latitude, time, ship MMSI, course, the speed of a ship or plane, and source includes bank base AIS data and satellite
AIS data.
9. the ship track method for detecting abnormality according to claim 1 based on navigation channel model, it is characterised in that: the step
In rapid 3, course line refers to the route between two destinations of connection, is described with a triple NL=(F, T, W), wherein F is course line
The destination being driven out to；T is the destination that course line is driven into, and F and T constitute the direction in course line, i.e. direction isW is time that course line occurred
Number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910433802.4A CN110210352B (en) | 2019-05-23 | 2019-05-23 | Ship track abnormity detection method based on channel model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910433802.4A CN110210352B (en) | 2019-05-23 | 2019-05-23 | Ship track abnormity detection method based on channel model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110210352A true CN110210352A (en) | 2019-09-06 |
| CN110210352B CN110210352B (en) | 2021-07-27 |
Family
ID=67788363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910433802.4A Active CN110210352B (en) | 2019-05-23 | 2019-05-23 | Ship track abnormity detection method based on channel model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110210352B (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111190978A (en) * | 2019-12-19 | 2020-05-22 | 北京海兰信数据科技股份有限公司 | Data processing method and device for offshore target object |
| CN111553291A (en) * | 2020-04-30 | 2020-08-18 | 北京爱笔科技有限公司 | Pedestrian trajectory generation method, device, equipment and computer storage medium |
| CN111694913A (en) * | 2020-06-05 | 2020-09-22 | 海南大学 | Ship AIS (automatic identification System) track clustering method and device based on convolution self-encoder |
| CN111884708A (en) * | 2020-07-29 | 2020-11-03 | 上海埃威航空电子有限公司 | Ship AIS data acquisition and fusion method based on low-orbit satellite and shore-based |
| CN111928855A (en) * | 2020-08-21 | 2020-11-13 | 上海船舶运输科学研究所 | Automatic shortest route planning method based on AIS data |
| CN111985529A (en) * | 2020-07-06 | 2020-11-24 | 东南大学 | Ship AIS track hybrid clustering method and system |
| CN112164247A (en) * | 2020-09-03 | 2021-01-01 | 重庆大学 | Ship route prediction method based on ship track clustering |
| CN112395382A (en) * | 2020-11-23 | 2021-02-23 | 武汉理工大学 | Ship abnormal track data detection method and device based on variational self-encoder |
| CN112556698A (en) * | 2020-12-17 | 2021-03-26 | 广州博进信息技术有限公司 | Ship behavior change and abnormality recognition method, equipment and medium |
| CN112699315A (en) * | 2020-12-30 | 2021-04-23 | 中南大学 | AIS data-based ship abnormal behavior detection method |
| CN113256146A (en) * | 2021-06-08 | 2021-08-13 | 广东嘉贸通科技有限公司 | Ship supervision method and system |
| CN113312438A (en) * | 2021-03-09 | 2021-08-27 | 中南大学 | Sea target position prediction method integrating airline extraction and trend judgment |
| CN113393707A (en) * | 2021-06-21 | 2021-09-14 | 广州嘉航通信科技有限公司 | Ship monitoring method, system, equipment and storage medium based on photoelectric linkage |
| CN113409617A (en) * | 2021-06-15 | 2021-09-17 | 中国水产科学研究院南海水产研究所 | Fishery ship yaw early warning system and method |
| CN113536948A (en) * | 2021-06-22 | 2021-10-22 | 武汉理工大学 | Fishing boat fishing behavior recognition method and device |
| CN113780952A (en) * | 2021-09-16 | 2021-12-10 | 上海船舶运输科学研究所 | Method and system for analyzing transport capacity of container liner ship route |
| CN113836118A (en) * | 2021-11-24 | 2021-12-24 | 亿海蓝（北京）数据技术股份公司 | Ship static data supplementing method and device, electronic equipment and readable storage medium |
| CN114020534A (en) * | 2021-11-05 | 2022-02-08 | 中远海运科技股份有限公司 | Shipping data snapshot generation method |
| CN114066354A (en) * | 2021-11-12 | 2022-02-18 | 中远海运科技股份有限公司 | Intelligent air route recommendation method and system based on global ship historical track |
| CN114090718A (en) * | 2022-01-11 | 2022-02-25 | 中国人民解放军海军工程大学 | Bi-LSTM prediction and fuzzy analysis based interrupted track correlation method |
| WO2022068417A1 (en) * | 2020-09-29 | 2022-04-07 | 南京北斗创新应用科技研究院有限公司 | Vessel loitering detection method based on ais data |
| CN114550498A (en) * | 2022-01-13 | 2022-05-27 | 武汉理工大学 | Intelligent early warning system for ship deviation channel driven by massive AIS data |
| CN114676180A (en) * | 2022-05-27 | 2022-06-28 | 中国人民解放军海军工程大学 | Synchronous disk-duplicating system and method for multi-machine cooperative underwater detection |
| CN114742128A (en) * | 2022-03-10 | 2022-07-12 | 交通运输部水运科学研究所 | Method, device, terminal and storage medium for identifying ship abnormal behavior |
| CN114862738A (en) * | 2022-06-06 | 2022-08-05 | 集美大学 | Traffic flow density self-adaptive ship track and electronic chart superposition fusion display method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07175935A (en) * | 1993-07-22 | 1995-07-14 | Philips Electron Nv | Digital picture processing method |
| CN108254741A (en) * | 2018-01-16 | 2018-07-06 | 中国人民解放军海军航空大学 | Targetpath Forecasting Methodology based on Recognition with Recurrent Neural Network |
| CN109543715A (en) * | 2018-10-23 | 2019-03-29 | 武汉理工大学 | A kind of ship air route is extracted and the method for track deviation detection |
| CN109697221A (en) * | 2018-11-22 | 2019-04-30 | 东软集团股份有限公司 | Method for digging, device, storage medium and the electronic equipment of track rule |
-
2019
- 2019-05-23 CN CN201910433802.4A patent/CN110210352B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07175935A (en) * | 1993-07-22 | 1995-07-14 | Philips Electron Nv | Digital picture processing method |
| CN108254741A (en) * | 2018-01-16 | 2018-07-06 | 中国人民解放军海军航空大学 | Targetpath Forecasting Methodology based on Recognition with Recurrent Neural Network |
| CN109543715A (en) * | 2018-10-23 | 2019-03-29 | 武汉理工大学 | A kind of ship air route is extracted and the method for track deviation detection |
| CN109697221A (en) * | 2018-11-22 | 2019-04-30 | 东软集团股份有限公司 | Method for digging, device, storage medium and the electronic equipment of track rule |
Non-Patent Citations (3)
| Title |
|---|
| 刘亚帅 等: "基于网格化的船舶航迹异常检测算法", 《雷达与对抗》 * |
| 姜志森 等: "基于AIS历史数据的异常船舶识别模型研究", 《技术与应用》 * |
| 牛敬华 等: "基于网格的航道模式提取算法研究", 《舰船电子工程》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111190978A (en) * | 2019-12-19 | 2020-05-22 | 北京海兰信数据科技股份有限公司 | Data processing method and device for offshore target object |
| CN111553291A (en) * | 2020-04-30 | 2020-08-18 | 北京爱笔科技有限公司 | Pedestrian trajectory generation method, device, equipment and computer storage medium |
| CN111553291B (en) * | 2020-04-30 | 2023-10-17 | 北京爱笔科技有限公司 | Pedestrian track generation method, device, equipment and computer storage medium |
| CN111694913B (en) * | 2020-06-05 | 2023-07-11 | 海南大学 | Ship AIS track clustering method and device based on convolution self-encoder |
| CN111694913A (en) * | 2020-06-05 | 2020-09-22 | 海南大学 | Ship AIS (automatic identification System) track clustering method and device based on convolution self-encoder |
| CN111985529A (en) * | 2020-07-06 | 2020-11-24 | 东南大学 | Ship AIS track hybrid clustering method and system |
| CN111985529B (en) * | 2020-07-06 | 2024-07-12 | 东南大学 | Ship AIS track hybrid clustering method and system |
| CN111884708A (en) * | 2020-07-29 | 2020-11-03 | 上海埃威航空电子有限公司 | Ship AIS data acquisition and fusion method based on low-orbit satellite and shore-based |
| CN111928855A (en) * | 2020-08-21 | 2020-11-13 | 上海船舶运输科学研究所 | Automatic shortest route planning method based on AIS data |
| CN112164247A (en) * | 2020-09-03 | 2021-01-01 | 重庆大学 | Ship route prediction method based on ship track clustering |
| WO2022068417A1 (en) * | 2020-09-29 | 2022-04-07 | 南京北斗创新应用科技研究院有限公司 | Vessel loitering detection method based on ais data |
| CN112395382A (en) * | 2020-11-23 | 2021-02-23 | 武汉理工大学 | Ship abnormal track data detection method and device based on variational self-encoder |
| CN112556698A (en) * | 2020-12-17 | 2021-03-26 | 广州博进信息技术有限公司 | Ship behavior change and abnormality recognition method, equipment and medium |
| CN112556698B (en) * | 2020-12-17 | 2023-12-15 | 广州博进信息技术有限公司 | Ship behavior change and abnormality identification method, equipment and medium |
| CN112699315A (en) * | 2020-12-30 | 2021-04-23 | 中南大学 | AIS data-based ship abnormal behavior detection method |
| CN112699315B (en) * | 2020-12-30 | 2023-08-15 | 中南大学 | AIS data-based ship abnormal behavior detection method |
| CN113312438B (en) * | 2021-03-09 | 2023-09-15 | 中南大学 | Marine target position prediction method integrating route extraction and trend judgment |
| CN113312438A (en) * | 2021-03-09 | 2021-08-27 | 中南大学 | Sea target position prediction method integrating airline extraction and trend judgment |
| CN113256146A (en) * | 2021-06-08 | 2021-08-13 | 广东嘉贸通科技有限公司 | Ship supervision method and system |
| CN113409617B (en) * | 2021-06-15 | 2023-02-17 | 中国水产科学研究院南海水产研究所 | Fishery ship yaw early warning system and method |
| CN113409617A (en) * | 2021-06-15 | 2021-09-17 | 中国水产科学研究院南海水产研究所 | Fishery ship yaw early warning system and method |
| CN113393707A (en) * | 2021-06-21 | 2021-09-14 | 广州嘉航通信科技有限公司 | Ship monitoring method, system, equipment and storage medium based on photoelectric linkage |
| CN113536948A (en) * | 2021-06-22 | 2021-10-22 | 武汉理工大学 | Fishing boat fishing behavior recognition method and device |
| CN113780952B (en) * | 2021-09-16 | 2024-03-15 | 上海船舶运输科学研究所有限公司 | Container airliner line capacity analysis method and system |
| CN113780952A (en) * | 2021-09-16 | 2021-12-10 | 上海船舶运输科学研究所 | Method and system for analyzing transport capacity of container liner ship route |
| CN114020534A (en) * | 2021-11-05 | 2022-02-08 | 中远海运科技股份有限公司 | Shipping data snapshot generation method |
| CN114066354B (en) * | 2021-11-12 | 2023-10-31 | 中远海运科技股份有限公司 | Intelligent route recommendation method and system based on global ship historical track |
| CN114066354A (en) * | 2021-11-12 | 2022-02-18 | 中远海运科技股份有限公司 | Intelligent air route recommendation method and system based on global ship historical track |
| CN113836118A (en) * | 2021-11-24 | 2021-12-24 | 亿海蓝（北京）数据技术股份公司 | Ship static data supplementing method and device, electronic equipment and readable storage medium |
| CN114090718A (en) * | 2022-01-11 | 2022-02-25 | 中国人民解放军海军工程大学 | Bi-LSTM prediction and fuzzy analysis based interrupted track correlation method |
| CN114550498A (en) * | 2022-01-13 | 2022-05-27 | 武汉理工大学 | Intelligent early warning system for ship deviation channel driven by massive AIS data |
| CN114742128A (en) * | 2022-03-10 | 2022-07-12 | 交通运输部水运科学研究所 | Method, device, terminal and storage medium for identifying ship abnormal behavior |
| CN114676180B (en) * | 2022-05-27 | 2022-09-30 | 中国人民解放军海军工程大学 | Synchronous multi-machine cooperative underwater detection repeater system and method |
| CN114676180A (en) * | 2022-05-27 | 2022-06-28 | 中国人民解放军海军工程大学 | Synchronous disk-duplicating system and method for multi-machine cooperative underwater detection |
| CN114862738A (en) * | 2022-06-06 | 2022-08-05 | 集美大学 | Traffic flow density self-adaptive ship track and electronic chart superposition fusion display method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110210352B (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210352A (en) | Ship track method for detecting abnormality based on navigation channel model | |
| Zhao et al. | Ship trajectories pre-processing based on AIS data | |
| CN113553682B (en) | Data-driven multi-level ship route network construction method | |
| Hörteborn et al. | A revisit of the definition of the ship domain based on AIS analysis | |
| Xin et al. | A simulation model for ship navigation in the “Xiazhimen” waterway based on statistical analysis of AIS data | |
| CN113537386B (en) | Ship typical motion trail self-adaptive mining method based on improved K-Medoids clustering | |
| Cheng et al. | Using big data to track marine oil transportation along the 21st-century Maritime Silk Road | |
| Yan et al. | Vessel movement analysis and pattern discovery using density-based clustering approach | |
| CN109697221A (en) | Method for digging, device, storage medium and the electronic equipment of track rule | |
| Virjonen et al. | Ship movement prediction using k-NN method | |
| Tang et al. | Detection of abnormal vessel behaviour based on probabilistic directed graph model | |
| CN115660137B (en) | Accurate estimation method for wind wave navigation energy consumption of ship | |
| CN114936332A (en) | Method and device for analyzing ship traffic flow in water area of wind power plant and storage medium | |
| Chang et al. | Vessel traffic analysis for maritime intelligent transportation system | |
| He et al. | Ship route planning using historical trajectories derived from AIS data | |
| CN114139642A (en) | Ship route extraction method combining ship journey semantic object and graph theory | |
| CN110084491A (en) | Based on the optimal air route blockage percentage appraisal procedure for passing through path under the conditions of convection weather | |
| Carlini et al. | Uncovering vessel movement patterns from AIS data with graph evolution analysis. | |
| Wen et al. | Spatio-temporal route mining and visualization for busy waterways | |
| He et al. | Mining channel water depth information from IoT-based big automated identification system data for safe waterway navigation | |
| Spiliopoulos et al. | Knowledge extraction from maritime spatiotemporal data: An evaluation of clustering algorithms on Big Data | |
| Xu et al. | Trajectory clustering for SVR-based Time of Arrival estimation | |
| Lei et al. | Trajectory data restoring: A way of visual analysis of vessel identity base on optics | |
| Weng et al. | Detection of abnormal ship trajectory based on the complex polygon | |
| Xia | Navigational risk analysis based on GIS spatiotemporal trajectory mining: a case study in Nanjing Yangtze River Bridge waters |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |